中島_backup の履歴(No.26)

B3 前期授業スケジュール

	月曜日	火曜日	水曜日	木曜日	金曜日
1-2					研究会
3-4		卒論1			研究会
5-6	卒論1	ディジタル信号処理	卒論1	卒論1
7-8					技術者倫理
9-10		研究会		&size(px){Text you want to change};
11-12

&ref(): File not found: "ダッシュストーム.jpg" at page "中島"; &ref(): File not found: "ダッシュストーム.jpg" at page "中島"; &ref(): File not found: "ダッシュストーム.jpg" at page "中島"; &ref(): File not found: "ダッシュストーム.jpg" at page "中島"; &ref(): File not found: "ダッシュストーム.jpg" at page "中島"; &ref(): File not found: "ダッシュストーム.jpg" at page "中島";

&ref(): File not found: "栗松.jpg" at page "中島"; &ref(): File not found: "栗松.jpg" at page "中島"; &ref(): File not found: "栗松.jpg" at page "中島"; &ref(): File not found: "栗松.jpg" at page "中島"; &ref(): File not found: "栗松.jpg" at page "中島"; &ref(): File not found: "栗松.jpg" at page "中島";

メモ

離散選択モデル　支払い意思　どんな条件があれば他の条件よりもお金を払えるか

ヘドニックアプローチ　価格に影響を与える要因を分析する

離散選択モデル　どのような属性の組み合わせが消費者に選ばれやすいのかを分析。　価格だけでなく、消費者選好の観点から選択確率を考慮することが可能

交絡因子の影響を排除することはできない。

→操作変数法を利用することで、未観測の交絡因子が存在しても、対象の要因・効果を推定する方法。

どのような消費者がある属性に対して強い選好を持っているか

→構造推定

3.3限界支払い意思額

変数選択法　種類
全探索法

逐次選択法
（前進選択法
後退選択法
ステップワイズ選択法）

正則化法
（リッジ回帰
ラッソ回帰
Elastic Net）

相関分析
主成分分析
boruta法
AIC/BICの最小化

import pandas as pd

# CSVファイルを読み込む
file_path = r"C:\Users\tn011\Downloads\富山取引のほう　富山市のみ 2\富山取引のほう　富山市のみ\df_housing_toyamacity.csv"
df = pd.read_csv(file_path)

# 元号から西暦への変換関数
def convert_gengo_to_seireki(gengo_year):
    if '令和' in gengo_year:
        year = int(gengo_year.replace('令和', ''))
        return 2018 + year  # 令和は2019年から
    elif '平成' in gengo_year:
        year = int(gengo_year.replace('平成', ''))
        return 1988 + year  # 平成は1989年から
    elif '昭和' in gengo_year:
        year = int(gengo_year.replace('昭和', ''))
        return 1925 + year  # 昭和は1926年から
    elif '大正' in gengo_year:
        year = int(gengo_year.replace('大正', ''))
        return 1911 + year  # 大正は1912年から
    elif '明治' in gengo_year:
        year = int(gengo_year.replace('明治', ''))
        return 1867 + year  # 明治は1868年から
    else:
        return None  # 元号が認識できない場合

# 例: '元号'という列が元号を含むと仮定
if '元号' in df.columns:
    df['西暦'] = df['元号'].apply(convert_gengo_to_seireki)

# 変換結果をCSVとして保存
output_path = r"C:\Users\tn011\Downloads\富山取引のほう　富山市のみ 2\富山取引のほう　富山市のみ\df_housing_toyamacity_with_seireki.csv"
df.to_csv(output_path, index=False)

import numbers
import warnings

import cvxpy
import numpy as np
from asgl import ASGL
from sklearn.base import MultiOutputMixin
from sklearn.base import RegressorMixin
from sklearn.exceptions import ConvergenceWarning
from sklearn.linear_model import ElasticNet
from sklearn.linear_model._coordinate_descent import _alpha_grid
from sklearn.utils import check_X_y
from sklearn.utils.validation import check_is_fitted

class AdaptiveElasticNet(ASGL, ElasticNet, MultiOutputMixin, RegressorMixin):
    """
    Objective function and parameters as described with modifications
    to allow alpha1, alpha2, l1_ratio1, and l1_ratio2 customization.
    """

def __init__(
        self,
        alpha1=0.021544346900318846,   # First-stage ElasticNet alpha
        alpha2=0.0009443498043343188,  # Second-stage ElasticNet alpha
        *,
        l1_ratio1=0.8889,  # First-stage ElasticNet L1 ratio
        l1_ratio2=0.778,  # Second-stage ElasticNet L1 ratio
        gamma=0.5,  # Weight adjustment exponent
        fit_intercept=True,
        precompute=False,
        max_iter=10000,
        copy_X=True,
        solver=None,
        tol=None,
        positive=False,
        positive_tol=1e-3,
        random_state=None,
        eps_coef=1e-6,
        verbose=True
    ):
        params_asgl = dict(model="lm", penalization="asgl")
        if solver is not None:
            params_asgl["solver"] = solver
        if tol is not None:
            params_asgl["tol"] = tol

super().__init__(**params_asgl)

self.alpha1 = alpha1
        self.alpha2 = alpha2
        self.l1_ratio1 = l1_ratio1
        self.l1_ratio2 = l1_ratio2
        self.gamma = gamma
        self.fit_intercept = fit_intercept
        self.max_iter = max_iter
        self.precompute = precompute
        self.copy_X = copy_X
        self.positive = positive
        self.positive_tol = positive_tol
        self.random_state = random_state
        self.eps_coef = eps_coef
        self.verbose = verbose

if not self.fit_intercept:
            raise NotImplementedError

def fit(self, X, y, check_input=True):
        if check_input:
            X_copied = self.copy_X and self.fit_intercept
            X, y = self._validate_data(
                X,
                y,
                accept_sparse="csc",
                order="F",
                dtype=[np.float64, np.float32],
                copy=X_copied,
                multi_output=True,
                y_numeric=True,
            )

# 第一段階の ElasticNet 実行
        enet_model_1 = self.elastic_net(self.l1_ratio1, alpha=self.alpha1)
        enet_model_1.fit(X, y)
        enet_coef = enet_model_1.coef_

# 重みの計算
        weights = 1.0 / (np.maximum(np.abs(enet_coef), self.eps_coef) ** self.gamma)

# 第二段階の最適化
        self.coef_, self.intercept_ = self._optimize_second_stage(X, y, weights)

# モデル属性を格納
        self.enet_coef_ = enet_coef
        self.weights_ = weights

return self

def predict(self, X):
        check_is_fitted(self, ["coef_", "intercept_"])
        return super(ElasticNet, self).predict(X)

def elastic_net(self, l1_ratio, **params):
        """
        Create an ElasticNet model with the specified parameters.
        """
        elastic_net = ElasticNet(l1_ratio=l1_ratio)

for k, v in self.get_params().items():
            try:
                elastic_net = elastic_net.set_params(**{k: v})
            except ValueError:
                pass  # Ignore parameters not supported by ElasticNet

elastic_net = elastic_net.set_params(**params)
        return elastic_net

def _optimize_second_stage(self, X, y, weights):
        """
        Perform second-stage optimization with adaptive weights.

Returns
        -------
        coef : np.array, shape (n_features,)
        intercept : float
        """
        n_samples, n_features = X.shape
        beta_variables = [cvxpy.Variable(n_features)]

model_prediction = 0.0
        if self.fit_intercept:
            beta_variables = [cvxpy.Variable(1)] + beta_variables
            ones = cvxpy.Constant(np.ones((n_samples, 1)))
            model_prediction += ones @ beta_variables[0]

# モデル予測
        model_prediction += X @ beta_variables[1]
        error = cvxpy.sum_squares(y - model_prediction) / (2 * n_samples)
        l1_coefs = self.alpha2 * self.l1_ratio2
        # 第二段階の正則化項
        l1_penalty = cvxpy.Constant(l1_coefs * weights) @ cvxpy.abs(
            beta_variables[1]
        )
        l2_penalty = (
            cvxpy.Constant(self.alpha1 * (1 - self.l1_ratio1))
            * cvxpy.sum_squares(beta_variables[1])
        )

constraints = [b >= 0 for b in beta_variables] if self.positive else []

# 最適化問題の定義
        problem = cvxpy.Problem(
            cvxpy.Minimize(error + l1_penalty + l2_penalty), constraints=constraints

n problem.solve(solver="OSQP", max_iter=self.max_iter)\n\n if problem.status != "optimal":\n raise ConvergenceWarning(\n f"Solver did not reach optimum (Status: {problem.status})"\n )\n\n beta_sol = np.concatenate([b.value for b in beta_variables], axis=0)\n beta_sol[np.abs(beta_sol) < self.tol] = 0\n\n intercept, coef = beta_sol[0], beta_sol[1:]\n coef = np.maximum(coef, 0) if self.positive else coef\n\n return coef, intercept\n\n\nfrom sklearn.linear_model import ElasticNetCV\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.datasets import make_regression\nimport numpy as np\nfrom sklearn.model_selection import train_test_split\nimport pandas as pd\nfrom sklearn.preprocessing import StandardScaler\n\n# CSVファイルのパスを指定してください\nfile_path = "C:/Users/nt011/Desktop/研究/富山取引のほう富山市のみ/変数選択/変数作成後新新.csv"\n\n# CSVファイルの読み込み\ndf = pd.read_csv(file_path, encoding='cp932') # 文字コードが異なる場合は、'utf-8' を他のエンコーディングに変更してください\n\n# 特徴量とターゲットの分割\nX = df.drop(columns=['取引価格（㎡単価）']) # 取引価格（㎡単価）をyとして分離\ny = df['取引価格（㎡単価）'] # ターゲット変数\n\n# 🔥 標準化の実施\nscaler_X = StandardScaler()\nscaler_y = StandardScaler()\n\nX_scaled = scaler_X.fit_transform(X) # Xの標準化\ny_scaled = scaler_y.fit_transform(y.values.reshape(-1, 1)).ravel() # yの標準化\n\n\n# データ分割\nX_train, X_test, y_train, y_test = train_test_split(X_scaled, y_scaled, test_size=0.35, random_state=42)\n\n# 訓練データの一部を使用\nX_sample, _, y_sample, _ = train_test_split(X_train, y_train, test_size=0.8, random_state=42)\n\n# 第一段階: ElasticNetCVを使用した最適パラメータの導出\nenet_cv = ElasticNetCV(\n l1_ratio=np.linspace(0.0001, 1, 25), # l1_ratioの候補\n alphas=np.logspace(-5, 0, 25), # alphaの候補\n cv=5, # 交差検証の分割数\n random_state=42,\n n_jobs=-1\n)\nenet_cv.fit(X_train, y_train)\n\n# 第一段階の最適パラメータと係数を取得\nalpha1_opt = enet_cv.alpha_\nl1_ratio1_opt = enet_cv.l1_ratio_\nenet_coef = enet_cv.coef_\n\nprint(f"第一段階の最適パラメータ: alpha1={alpha1_opt}, l1_ratio1={l1_ratio1_opt}"))

やること

from sklearn.linear_model import ElasticNet
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import make_regression
import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

# CSVファイルのパスを指定してください
file_path = "C:/Users/nt011/Desktop/研究/富山取引のほう富山市のみ/変数選択/変数作成後新.csv"

# CSVファイルの読み込み
df = pd.read_csv(file_path, encoding='cp932')  # 文字コードが異なる場合は、'utf-8' を他のエンコーディングに変更してください

# 特徴量とターゲットの分割
X = df.drop(columns=['取引価格（㎡単価）'])  # 取引価格（㎡単価）をyとして分離
y = df['取引価格（㎡単価）']  # ターゲット変数

# 🔥 標準化の実施
scaler_X = StandardScaler()
scaler_y = StandardScaler()

X_scaled = scaler_X.fit_transform(X)  # Xの標準化
y_scaled = scaler_y.fit_transform(y.values.reshape(-1, 1)).ravel()  # yの標準化

# データ分割
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y_scaled, test_size=0.2, random_state=42)

# 訓練データの一部を使用
X_sample, _, y_sample, _ = train_test_split(X_train, y_train, test_size=0.8, random_state=42)

# 2. パラメータグリッドの設定
param_grid = {
    'alpha': np.logspace(-5, 0, 10),  # alpha1の探索範囲 (正則化パラメータ)
    'l1_ratio': np.linspace(0.0001, 1.0, 10)  # l1_ratio1の探索範囲 (L1とL2の比率)
}

# パラメータ名を変更（alpha -> alpha1, l1_ratio -> l1_ratio1）
param_grid = {'alpha1': param_grid['alpha'], 'l1_ratio1': param_grid['l1_ratio']}

# 3. ElasticNetモデルの初期化
elastic_net = ElasticNet(max_iter=10000, random_state=42)

# 4. グリッドサーチCVの設定
grid_search = GridSearchCV(
    estimator=elastic_net,
    param_grid={'alpha': param_grid['alpha1'], 'l1_ratio': param_grid['l1_ratio1']},  # 変更した名前に対応
    cv=5,  # 5分割交差検証
    scoring='neg_mean_squared_error',  # 評価指標: 平均二乗誤差の負値
    verbose=1,
    n_jobs=-1  # 並列実行
)

# 5. グリッドサーチの実行
grid_search.fit(X_sample, y_sample)

# 6. 最適なパラメータとスコアの取得
best_params = grid_search.best_params_
best_params_renamed = {'alpha1': best_params['alpha'], 'l1_ratio1': best_params['l1_ratio']}
best_score = grid_search.best_score_

print("最適なパラメータ:")
print(best_params_renamed)
print("最良のスコア (平均二乗誤差の負値):")
print(best_score)

class TQDMGridSearchCV(GridSearchCV):
    def __init__(self, estimator, param_grid, cv=5, scoring=None, n_jobs=None, verbose=0, 
                 refit=True, return_train_score=True, pre_dispatch='2*n_jobs', error_score='raise', **kwargs):
        # iid引数を削除して、super()に渡さない
        super().__init__(estimator=estimator, param_grid=param_grid, cv=cv, scoring=scoring,
                         n_jobs=n_jobs, verbose=verbose, refit=refit, return_train_score=return_train_score,
                         pre_dispatch=pre_dispatch, error_score=error_score, **kwargs)
        
        # tqdmを使って進捗表示
        self.tqdm = tqdm(total=1, position=0, leave=True)
    
    def fit(self, X, y=None, **fit_params):
        # 進捗バーを更新
        self.tqdm.set_description("Fitting model")
        
        result = super().fit(X, y, **fit_params)
        
        self.tqdm.close()  # 進捗バーを閉じる
        return result

# 第二段階のGridSearchCVで交差検証（進捗表示を追加）
grid_search = TQDMGridSearchCV(
    estimator=model,
    param_grid=param_grid,
    cv=5,  # 交差検証の分割数
    scoring='neg_mean_squared_error',  # 評価指標（MSEの負の値を使用）
    #n_jobs=-1,  # 並列実行
    verbose=1   # 実行状況を表示しない
)

import numba
from numba import jit
import numpy as np
import pandas as pd
from sklearn.linear_model import ElasticNet
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import cross_val_score

# Numbaを使った交差検証の高速化

@jit(nopython=True)
def cross_val_score_numba(X, y, model, cv=5):
    """
    Numbaを使用した交差検証の実装
    """
    n_samples = X.shape[0]
    fold_size = n_samples // cv
    scores = np.zeros(cv)
    
    for i in range(cv):
        # フォールドの分割
        val_idx = list(range(i * fold_size, (i + 1) * fold_size))
        train_idx = list(set(range(n_samples)) - set(val_idx))
        
        X_train, X_val = X[train_idx], X[val_idx]
        y_train, y_val = y[train_idx], y[val_idx]
        
        model.fit(X_train, y_train)
        y_pred = model.predict(X_val)
        
        # MSEスコアの計算
        scores[i] = mean_squared_error(y_val, y_pred)
    
    return scores

# CSVファイルのパスを指定してください
file_path = "C:/Users/tn011/Desktop/変数作成後新新.csv"

# CSVファイルの読み込み
df = pd.read_csv(file_path, encoding='cp932')

# 特徴量とターゲットの分割
X = df.drop(columns=['取引価格（㎡単価）'])
y = df['取引価格（㎡単価）']

# 標準化の実施
scaler_X = StandardScaler()
scaler_y = StandardScaler()

X_scaled = scaler_X.fit_transform(X)
y_scaled = scaler_y.fit_transform(y.values.reshape(-1, 1)).ravel()

# 訓練データとテストデータに分割
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y_scaled, test_size=0.35, random_state=42)

# 第一段階のElasticNetのハイパーパラメータチューニング
alpha_values = np.logspace(-5, 0, 25)
l1_ratio_values = np.linspace(0.0001, 1, 25)

best_score = float('inf')
best_alpha = None
best_l1_ratio = None
best_model = None

# numbaを使用した交差検証を実行
for alpha in alpha_values:
    for l1_ratio in l1_ratio_values:
        model = ElasticNet(alpha=alpha, l1_ratio=l1_ratio, max_iter=10000)
        
        scores = cross_val_score(model, X_train, y_train, cv=5, scoring='neg_mean_squared_error')
        
        mean_score = np.mean(scores)
        
        if mean_score < best_score:
            best_score = mean_score
            best_alpha1 = alpha
            best_l1_ratio1 = l1_ratio
            best_model = model

print(f"最適なalpha: {best_alpha1}, 最適なl1_ratio: {best_l1_ratio1}")

# 最適なモデルのトレーニング
best_model.fit(X_train, y_train)
y_pred = best_model.predict(X_test)

# テストデータでの性能を評価
test_score = mean_squared_error(y_test, y_pred)
print(f"テストデータのMSE: {test_score}")

高速化
import numbers
import warnings
from numba import njit, prange
import numpy as np
import cvxpy
from asgl import ASGL
from sklearn.base import MultiOutputMixin
from sklearn.base import RegressorMixin
from sklearn.exceptions import ConvergenceWarning
from sklearn.linear_model import ElasticNet
from sklearn.utils import check_X_y
from sklearn.utils.validation import check_is_fitted
from numba import njit, prange

class AdaptiveElasticNet(ASGL, ElasticNet, MultiOutputMixin, RegressorMixin):
    """
    Adaptive ElasticNet implementation with customizable parameters.
    """
    def __init__(
        self,
        alpha1=0.008,  # First-stage ElasticNet alpha
        alpha2=0.0009443498043343188,  # Second-stage ElasticNet alpha
        *,
        l1_ratio1=0.875,  # First-stage ElasticNet L1 ratio
        l1_ratio2=0.778,  # Second-stage ElasticNet L1 ratio
        gamma=0.5,  # Weight adjustment exponent
        fit_intercept=True,
        precompute=False,
        max_iter=5000,
        copy_X=True,
        solver=None,
        tol=None,
        positive=False,
        positive_tol=1e-3,
        random_state=None,
        eps_coef=1e-6,
        verbose=True,
    ):
        params_asgl = dict(model="lm", penalization="asgl")
        if solver is not None:
            params_asgl["solver"] = solver
        if tol is not None:
            params_asgl["tol"] = tol

super().__init__(**params_asgl)

if not self.fit_intercept:
            raise NotImplementedError

@staticmethod
    @njit(parallel=True)
    def adaptive_weight_calculation(coef, eps_coef, gamma):
        """
        Accelerated weight calculation using numba.
        """
        weights = np.empty_like(coef)
        for i in prange(len(coef)):
            weights[i] = 1.0 / (max(abs(coef[i]), eps_coef) ** gamma)
        return weights
    
    def fit(self, X, y, check_input=True):
        if check_input:
            X_copied = self.copy_X and self.fit_intercept
            X, y = self._validate_data(
                X,
                y,
                accept_sparse="csc",
                order="F",
                dtype=[np.float64, np.float32],
                copy=X_copied,
                multi_output=True,
                y_numeric=True,
            )

# First-stage ElasticNet
        enet_model_1 = self.elastic_net(self.l1_ratio1, alpha=self.alpha1)
        enet_model_1.fit(X, y)
        enet_coef = enet_model_1.coef_

# Compute adaptive weights
        weights = self.adaptive_weight_calculation(enet_coef, self.eps_coef, self.gamma)

# Second-stage optimization
        self.coef_, self.intercept_ = self._optimize_second_stage(X, y, weights)

# Store model attributes
        self.enet_coef_ = enet_coef
        self.weights_ = weights

return self

def predict(self, X):
        check_is_fitted(self, ["coef_", "intercept_"])
        return super(ElasticNet, self).predict(X)

def elastic_net(self, l1_ratio1, **params):
        """
        Create an ElasticNet model with the specified parameters.
        """
        elastic_net = ElasticNet(l1_ratio=l1_ratio1)

for k, v in self.get_params().items():
            try:
                elastic_net = elastic_net.set_params(**{k: v})
            except ValueError:
                pass

elastic_net = elastic_net.set_params(**params)
        return elastic_net
    
    @staticmethod
    @njit(parallel=True, fastmath=True)
    def fista(X, y, weights, alpha1, l1_ratio1, alpha2, l1_ratio2, max_iter=5000, tol=1e-6):
        """
    FISTAによる適応ElasticNetの第2段階最適化処理。
    
    Parameters
    ----------
    X : ndarray
        特徴量行列 (n_samples, n_features)
    y : ndarray
        目的変数 (n_samples,

1段階のElasticNetの正則化係数\n l1_ratio1 : float\n 第1段階のL1比率\n alpha2 : float\n 第2段階のElasticNetの正則化係数\n l1_ratio2 : float\n 第2段階のL1比率\n max_iter : int, optional\n 最大反復回数 (default=5000)\n tol : float, optional\n 収束許容誤差 (default=1e-6)\n\n Returns\n -------\n beta : ndarray\n 推定された係数 (n_features,)\n """\n\n n_samples, n_features = X.shape\n beta = np.zeros(n_features) # 係数の初期化\n beta_old = beta.copy()\n t = 1\n\n # Lipschitz定数の計算（手動でL2ノルム計算）\n L = np.sqrt(np.sum(X**2)) ** 2 / n_samples \n\n # L2 正則化項（第一段階のパラメータを利用）\n L2_penalty = alpha1 * (1 - l1_ratio1)\n\n for _ in prange(max_iter):\n # 勾配計算\n grad = -X.T @ (y - X @ beta) / n_samples \n\n # ソフトしきい値処理（L1 正則化）\n z = beta - grad / L\n shrink = alpha2 * l1_ratio2 * weights / L\n beta_new = np.sign(z) * np.maximum(np.abs(z) - shrink, 0)\n\n # Nesterov 加速\n t_new = (1 + np.sqrt(1 + 4 * t ** 2)) / 2\n beta = beta_new + *1.ravel()\n\n# Split data\nX_train, X_test, y_train, y_test = train_test_split(X_scaled, y_scaled, test_size=0.35, random_state=42)\n\n# 訓練データの一部を使用\nX_sample, _, y_sample, _ = train_test_split(X_train, y_train, test_size=0.8, random_state=42)\n\n# First-stage ElasticNet\nmodel = AdaptiveElasticNet(alpha1=0.00825404185268019, l1_ratio1=0.8750125, gamma=0.5)\n\n# Second-stage parameter grid\nparam_grid = {\n "alpha2": np.logspace(-4, 0, 5),\n "l1_ratio2": np.linspace(0.0001, 1.0, 5),\n}\n\n# GridSearchCV with accelerated weight calculation\ngrid_search = GridSearchCV(\n estimator=model,\n param_grid=param_grid,\n cv=3,\n scoring="neg_mean_squared_error",\n n_jobs=-1,\n verbose=1,\n)\n\n# Fit GridSearchCV\ngrid_search.fit(X_sample, y_sample)\n\n# Output best parameters and score\nprint(f"Best parameters: {grid_search.best_params_}")\nprint(f"Best negative MSE: {grid_search.best_score_}")\n)

研究会(中島)

専門ゼミ(中島)

引き継ぎ(中島)

メモ(中島)

中間発表(中島)

中間発表システムまとめ(中島)

本論(中島)

B3 前期授業スケジュール